Milling cutter condition monitoring using machine learning approach

Abstract

The cutting tool condition drives the economy of machining processes in manufacturing industry. The failures in cutting tool are unbearable and affect the drive of machine tool which reduces life. Hence it necessitates reducing power consumption using monitoring cutting tool condition and hence requires an efficient supervision to monitor and predict faults. Simply stated, the condition which curtails cutting tool life highlighted before it turns into a tool wear, breakage and failure. This ensures optimized and effective use of a cutting tool, saves maintenance/repair time, enhances constancy in a process etc. The recent development in Machine Learning (ML) and its applicability for condition monitoring approach has drawn attention of researchers. Machine learning examines existing and past indications to predict conditions in future. This paper presents machine learning based condition monitoring of milling cutter of vertical machining centre (VMC). The vibration signals acquisition of 4 insert milling cutter is carried out with healthy and various fault conditions. The Visual Basic (VB) code and script is used to extract statistical features and decision tree algorithm is used to select relevant features. The different conditions of milling cutter are classified using tree family classifiers. The effort made in this work is to check applicability of ML approach for milling cutter fault diagnosis for reducing power consumption of drive of machine tool.

Application of Machine Learning for Tool Condition Monitoring in Turning

“…In tune with this, the accelerometer needs to be placed closer to the posting of a tool. A vibration with a component in the direction of cutting is best responsive to the tool wear as compared to the others, for that reason the accelerometer was [3][4][5]. The data logger is developed using a microcontroller Arduino ATmega2560 and a computer for acquiring, conditioning, processing and storing the data from the accelerometer.…”

“…Cutting may edge itself individual might be dulling of very fast without any this effect manifesting itself before that itself, those things are not considered when dealing with the gradual phenomenon of wear this takes place very gradually. This is because the tool deteriorates quality when it is being put to use where the chip is rubbing against the rake surface while moving and also applying a considerable amount of force very frequently in the order of hundreds of neutrons [3][4][5]. A Tool Condition Monitoring (TCM) is a predictive maintenance system used for mechanical systems or machine tools that monitor the condition of a cutting tool.…”

Development of Deep Belief Network for Tool Faults Recognition

“…The index was analyzed using the counter-propagative neural net. Recently, Patange et al [ 28 ] suggested an ML approach to diagnose the condition of a milling cutter. Relevant features were selected from a decision tree and for several tool conditions and classified using a random forest tree algorithm.…”

Study of Cutting Power and Power Efficiency during Straight-Tooth Cylindrical Milling Process of Particle Boards

“…Different modelling techniques (such as artificial neural networks (ANNs), deep learning (DL), machine learning (ML), etc.) have been studied to monitor tool conditions, reduce cutting power consumption and increase energetic efficiency [26][27][28][29][30][31]. Tiryaki et al employed artificial neural networks to minimize the surface roughness and power consumption of wood abrasive machining processes.…”